A Comparative Analysis of Convolutional Neural Network Architectures for Binary Image Classification: A Case Study in Skin Cancer Detection

Authors : Şerife Gül Korkut, Hatice Kocabaş, Rifat Kurban

Pages : 2008-2022

Doi:10.31466/kfbd.1515451

View : 83 | Download : 69

Publication Date : 2024-12-15

Article Type : Research Paper

Abstract :In this study, a comprehensive comparative analysis of Convolutional Neural Network (CNN) architectures for binary image classification is presented with a particular focus on the benefits of transfer learning. The performance and accuracy of prominent CNN models, including MobileNetV3, VGG19, ResNet50, and EfficientNetB0, in classifying skin cancer from binary images are evaluated. Using a pre-trained approach, the impact of transfer learning on the effectiveness of these architectures and identify their strengths and weaknesses within the context of binary image classification are investigated. This paper aims to provide valuable insights for selecting the optimal CNN architecture and leveraging transfer learning to achieve superior performance in binary image classification applications, particularly those related to medical image analysis.
Keywords : Evrişimsel Sinir Ağları (CNN, Transfer Öğrenimi, İkili Görüntü Sınıflandırma, CNN Mimari Karşılaştırması, Cilt Kanseri Tespiti